DeepForgeby svx

0/5730 solved

← All interview tracks

MLE · applied scientistsApplied ML · deep learning · optimization

General · Machine Learning Engineer

Classic supervised learning and deep learning: losses and gradients, k-means and trees, normalization layers, and batch optimizers.

3 phases · 26 problems · 26 unique

Start timed mock5 problems · 4 min each

Your progress

0/26 · 0%

Continue track · Logistic Sigmoid

1Warm-up

0/8

Logistic Sigmoid
ml-002ML Fundamentals
Easy
K-Nearest Neighbors
ml-004ML Fundamentals
Medium
Accuracy
ml-008ML Fundamentals
Easy
MSE Gradient
ml-012ML Fundamentals
Medium
Mean Squared Error
ml-017ML Fundamentals
Easy
ReLU
dl-001Deep Learning
Easy
Numerically Stable Softmax
dl-003Deep Learning
Medium
Gradient Descent
op-001Optimization
Medium

2Core

0/10

Binary Cross-Entropy Loss
ml-014ML Fundamentals
Medium
K-Means Assignment Step
ml-032ML Fundamentals
Medium
K-Means Inertia
ml-034ML Fundamentals
Medium
Gaussian Naive Bayes Likelihood
ml-037ML Fundamentals
Medium
MLP Forward Pass
dl-004Deep Learning
Medium
Max Pooling Forward
dl-024Deep Learning
Medium
LayerNorm Forward
dl-027Deep Learning
Medium
TF-IDF
nlp-003NLP
Medium
Momentum Optimizer
op-003Optimization
Medium
Generic Adam Update
op-010Optimization
Medium

3Hard

0/8

K-Means One Iteration
ml-003ML Fundamentals
Hard
Best Decision Tree Split
ml-005ML Fundamentals
Hard
2D Linear Regression via Normal Equation
ml-011ML Fundamentals
Hard
Ridge Regression Closed Form
ml-013ML Fundamentals
Hard
K-Means++ Init
ml-145ML Fundamentals
Hard
Backprop Gradient
dl-005Deep Learning
Hard
Mini-Batch SGD for Linear Regression
op-002Optimization
Hard
Adam Optimizer
op-004Optimization
Hard